import numpy as np
from sklearn.linear_model import RidgeCV, Ridge
from sklearn.datasets import load_boston
from sklearn.preprocessing import scale

boston = scale(load_boston().data)
target = load_boston().target
alphas = np.linspace(0.1, 200)
weight = np.logspace(0, -2, len(target))

print "RidgeCV(eigen)"
fit0 = RidgeCV(alphas=alphas, store_cv_values=True, gcv_mode='eigen').fit(boston, target, sample_weight=weight)    
print "alpha:", fit0.alpha_
print "cv:", fit0.cv_values_[0,0:5]
print "coef:", fit0.coef_[:5]

print "RidgeCV(svd)"
fit1 = RidgeCV(alphas=alphas, store_cv_values=True, gcv_mode='svd').fit(boston, target, sample_weight=weight)    
print "alpha:", fit1.alpha_
print "cv:", fit1.cv_values_[0,0:5]
print "coef:", fit1.coef_[:5]

print "Ridge"
fit2 = Ridge(fit0.alpha_).fit(boston, target, sample_weight=weight)
print "coef:", fit2.coef_[:5]

RidgeCV(eigen)
alpha: 167.363265306
cv: [ 1.63311277  1.58236816  1.53267447  1.48401844  1.43638695]
coef: [-0.90546722  1.0438252   0.09577594  0.68459321 -2.00971137]

RidgeCV(svd)
alpha: 167.363265306
cv: [ 1.63311277  1.58236816  1.53267447  1.48401844  1.43638695]
coef: [-0.90546722  1.0438252   0.09577594  0.68459321 -2.00971137]

Ridge
coef: [-0.11587241  0.37139676 -0.35468307  0.26534304 -0.29640185]